Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.

Migrate Cloudflare Sandbox apps from stable @cloudflare/sandbox to @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-next for apps already on the preview.

No description yet.

Run AI coding agents (Claude Code, OpenAI Codex, GitHub Copilot CLI) inside Docker against a dedicated Git worktree.

Remote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover.

MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

The official command line for Praxis (知行云): models, agents, sandboxes, search and data from one terminal.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Fix and diagnose DeepSeek Harness on native Windows. Official PowerShell, Workspace Write, shortcuts, and legacy preset repair. No WSL.

Access gate for AI coding harnesses (DSH plugin + Claude Code hook): per-directory deny/read/full, roster groups, audit log, model-facing tools with owner-approved widening.

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.

Shardflux MCP server (stdio): serverless VMs for your agent. Open a persistent workspace by key, run commands, edit files, use git, a browser and a desktop in it. Uses your scoped Shardflux API key.

Patch-style file editing for DeepSeek Harness: one apply_patch tool accepting git/unified diff (default) and Codex apply_patch syntax (opt-in), with all-or-nothing application, read-before-write intent dance, sandbox-aware delete/move, (declarative volat

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Official Huawei Cloud plugin for AI agents — skills, MCP tools, safety guardrails, and cloud sandbox to help AI agents build, deploy, and operate on Huawei Cloud securely.

`HarnessV1` adapter backed by [`@anthropic-ai/claude-agent-sdk`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk), which drives the `claude` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSo

Music video player for DeepSeek Harness Desktop: text, Canvas2D and WebGL2 3D scenes synced to your own audio. Sandboxed workshop packs can include licensed bilingual lyrics, timing and visual assets; only music is user-provided. Plugin code MIT; no song

A CLI that turns a goal into a pull request - and a sandbox for testing concurrent AI coding agents on the Mozaik runtime.

Enables agents to reach pump.fun's full API surface — official developer routes, bonding-curve reads, Solana RPC, and unsigned trade building — by writing JavaScript against one merged OpenAPI document, using just two tools (search and execute). Model-authored code runs in a network-less sandbox, so multi-step questions resolve in a single round trip while credentials stay on the host Worker.

Enables MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/awaiting-input/exited states. Sessions run inside a Seatbelt sandbox with command policies, human approvals, secret redaction, and hash-chained audit logging.